{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T21:41:53Z","timestamp":1775166113308,"version":"3.50.1"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Research Programs of Henan Science and Technology Department","award":["252102210034\uff0c232102210054"],"award-info":[{"award-number":["252102210034\uff0c232102210054"]}]},{"name":"Research Programs of Henan Science and Technology Department","award":["252102210034\uff0c232102210054"],"award-info":[{"award-number":["252102210034\uff0c232102210054"]}]},{"name":"Henan Province key research and development project","award":["231111212000"],"award-info":[{"award-number":["231111212000"]}]},{"name":"Supported by Henan Center for Outstanding Overseas Scientists","award":["GZS2022011"],"award-info":[{"award-number":["GZS2022011"]}]},{"DOI":"10.13039\/501100005230","name":"Chongqing Natural Science Foundation","doi-asserted-by":"crossref","award":["CSTB2023NSCQ-MSX0070"],"award-info":[{"award-number":["CSTB2023NSCQ-MSX0070"]}],"id":[{"id":"10.13039\/501100005230","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Aviation Science Foundation","award":["20230001055002"],"award-info":[{"award-number":["20230001055002"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s11554-025-01761-4","type":"journal-article","created":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T17:16:23Z","timestamp":1757697383000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["WT-DETR: Wavelet-enhanced DETR for robust tiny object detection via multi-scale feature optimization"],"prefix":"10.1007","volume":"22","author":[{"given":"Xiaoyan","family":"Shao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiqin","family":"Diao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingling","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuezhuan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Mei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zonghao","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,12]]},"reference":[{"key":"1761_CR1","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"1761_CR2","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L.M., Shum, H.-Y.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)"},{"key":"1761_CR3","doi-asserted-by":"crossref","unstructured":"Finder, S.E., Amoyal, R., Treister, E., Freifeld, O.: Wavelet convolutions for large receptive fields. In: European Conference on Computer Vision, pp.\u00a0363\u2013380, Springer, (2025)","DOI":"10.1007\/978-3-031-72949-2_21"},{"key":"1761_CR4","unstructured":"Khalfaoui-Hassani, I., Pellegrini, T., Masquelier, T.: Dilated convolution with learnable spacings. arXiv preprint arXiv:2112.03740 (2021)"},{"key":"1761_CR5","unstructured":"Ning, J., Spratling, M.: \u201cThe importance of anti-aliasing in tiny object detection,\u201d in Asian Conference on Machine Learning, pp.\u00a0975\u2013990, PMLR, (2024)"},{"key":"1761_CR6","doi-asserted-by":"crossref","unstructured":"Gong, Y., Yu, X., Ding, Y., Peng, X., Zhao, J., Han, Z.: Effective fusion factor in fpn for tiny object detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp.\u00a01160\u20131168, (2021)","DOI":"10.1109\/WACV48630.2021.00120"},{"key":"1761_CR7","doi-asserted-by":"crossref","unstructured":"Yang, C., Huang, Z., Wang, N.: Querydet: Cascaded sparse query for accelerating high-resolution small object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.\u00a013668\u201313677, (2022)","DOI":"10.1109\/CVPR52688.2022.01330"},{"key":"1761_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103430","volume":"106","author":"A Nazir","year":"2020","unstructured":"Nazir, A., Cheema, M.N., Sheng, B., Li, P., Li, H., Yang, P., Jung, Y., Qin, J., Feng, D.D.: SPST-CNN: spatial pyramid based searching and tagging of liver\u2019s intraoperative live views via CNN for minimal invasive surgery. J. Biomed. Inform. 106, 103430 (2020)","journal-title":"J. Biomed. Inform."},{"key":"1761_CR9","first-page":"1028","volume":"33","author":"A Liu","year":"2019","unstructured":"Liu, A., Liu, X., Fan, J., Ma, Y., Zhang, A., Xie, H., Tao, D.: Perceptual-sensitive GAN for generating adversarial patches. Proc. AAAI Conf. Artif. Intell. 33, 1028\u20131035 (2019)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"1761_CR10","doi-asserted-by":"crossref","unstructured":"Bai, Y., Zhang, Y., Ding, M., Ghanem, B.: SOD-MTGAN: small object detection via multi-task generative adversarial network. In: Proceedings of the European conference on computer vision (ECCV), pp.\u00a0206\u2013221, (2018)","DOI":"10.1007\/978-3-030-01261-8_13"},{"key":"1761_CR11","doi-asserted-by":"crossref","unstructured":"Noh, J., Bae, W., Lee, W., Seo, J., Kim, G.: Better to follow, follow to be better: towards precise supervision of feature super-resolution for small object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp.\u00a09725\u20139734, (2019)","DOI":"10.1109\/ICCV.2019.00982"},{"key":"1761_CR12","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.\u00a03588\u20133597, (2018)","DOI":"10.1109\/CVPR.2018.00378"},{"key":"1761_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, R., Shan, S., Chen, X.: Structure inference net: object detection using scene-level context and instance-level relationships. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.\u00a06985\u20136994, (2018)","DOI":"10.1109\/CVPR.2018.00730"},{"issue":"9","key":"1761_CR14","doi-asserted-by":"publisher","first-page":"3848","DOI":"10.1109\/TITS.2019.2935152","volume":"21","author":"L Zhao","year":"2019","unstructured":"Zhao, L., Song, Y., Zhang, C., Liu, Y., Wang, P., Lin, T., Deng, M., Li, H.: T-GCN: a temporal graph convolutional network for traffic prediction. IEEE Trans. Intell. Transp. Syst. 21(9), 3848\u20133858 (2019)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"5","key":"1761_CR15","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1016\/j.vrih.2022.08.007","volume":"4","author":"Y Zhao","year":"2022","unstructured":"Zhao, Y., Zhang, H., Lu, P., Li, P., Wu, E., Sheng, B.: DSD-MatchingNet: deformable sparse-to-dense feature matching for learning accurate correspondences. Virtual Real. Intell. Hardw. 4(5), 432\u2013443 (2022)","journal-title":"Virtual Real. Intell. Hardw."},{"key":"1761_CR16","doi-asserted-by":"crossref","unstructured":"Kisantal, M.: Augmentation for small object detection. arXiv preprint arXiv:1902.07296 (2019)","DOI":"10.5121\/csit.2019.91713"},{"key":"1761_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108998","volume":"133","author":"B Bosquet","year":"2023","unstructured":"Bosquet, B., Cores, D., Seidenari, L., Brea, V.M., Mucientes, M., Del Bimbo, A.: A full data augmentation pipeline for small object detection based on generative adversarial networks. Pattern Recogn. 133, 108998 (2023)","journal-title":"Pattern Recogn."},{"key":"1761_CR18","doi-asserted-by":"crossref","unstructured":"Daubechies, I.: Ten lectures on wavelets. Society for Industrial and Applied Mathematics (1992)","DOI":"10.1137\/1.9781611970104"},{"issue":"1","key":"1761_CR19","doi-asserted-by":"publisher","first-page":"119","DOI":"10.3390\/e23010119","volume":"23","author":"T Wang","year":"2021","unstructured":"Wang, T., Lu, C., Sun, Y., Yang, M., Liu, C., Ou, C.: Automatic ECG classification using continuous wavelet transform and convolutional neural network. Entropy 23(1), 119 (2021)","journal-title":"Entropy"},{"key":"1761_CR20","doi-asserted-by":"crossref","unstructured":"Huang, H., He, R., Sun, Z., Tan, T.: Wavelet-SRNet: a wavelet-based CNN for multi-scale face super resolution. In: Proceedings of the IEEE International Conference on Computer Vision, pp.\u00a01689\u20131697 (2017)","DOI":"10.1109\/ICCV.2017.187"},{"key":"1761_CR21","doi-asserted-by":"crossref","unstructured":"Guo, T., Seyed\u00a0Mousavi, H., Huu\u00a0Vu, T., Monga, V.: Deep wavelet prediction for image super-resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp.\u00a0104\u2013113 (2017)","DOI":"10.1109\/CVPRW.2017.148"},{"key":"1761_CR22","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1016\/j.patcog.2016.11.015","volume":"64","author":"Y Duan","year":"2017","unstructured":"Duan, Y., Liu, F., Jiao, L., Zhao, P., Zhang, L.: Sar image segmentation based on convolutional-wavelet neural network and Markov random field. Pattern Recogn. 64, 255\u2013267 (2017)","journal-title":"Pattern Recogn."},{"key":"1761_CR23","first-page":"478","volume":"35","author":"F Guth","year":"2022","unstructured":"Guth, F., Coste, S., De Bortoli, V., Mallat, S.: Wavelet score-based generative modeling. Adv. Neural. Inf. Process. Syst. 35, 478\u2013491 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1761_CR24","first-page":"20592","volume":"35","author":"SE Finder","year":"2022","unstructured":"Finder, S.E., Zohav, Y., Ashkenazi, M., Treister, E.: Wavelet feature maps compression for image-to-image CNNs. Adv. Neural. Inf. Process. Syst. 35, 20592\u201320606 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1761_CR25","doi-asserted-by":"crossref","unstructured":"Liu, P., Zhang, H., Zhang, K., Lin, L., Zuo, W.: Multi-level wavelet-CNN for image restoration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp.\u00a0773\u2013782 (2018)","DOI":"10.1109\/CVPRW.2018.00121"},{"key":"1761_CR26","doi-asserted-by":"publisher","first-page":"7074","DOI":"10.1109\/TIP.2021.3101395","volume":"30","author":"Q Li","year":"2021","unstructured":"Li, Q., Shen, L., Guo, S., Lai, Z.: Wavecnet: wavelet integrated CNNs to suppress aliasing effect for noise-robust image classification. IEEE Trans. Image Process. 30, 7074\u20137089 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"1761_CR27","unstructured":"Fujieda, S., Takayama, K., Hachisuka, T.: Wavelet convolutional neural networks. arXiv preprint arXiv:1805.08620 (2018)"},{"key":"1761_CR28","doi-asserted-by":"crossref","unstructured":"Chen, Y., Fan, H., Xu, B., Yan, Z., Kalantidis, Y., Rohrbach, M., Yan, S., Feng, J.: Drop an octave: reducing spatial redundancy in convolutional neural networks with octave convolution. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp.\u00a03435\u20133444 (2019)","DOI":"10.1109\/ICCV.2019.00353"},{"key":"1761_CR29","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp.\u00a0213\u2013229, Springer, (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1761_CR30","doi-asserted-by":"crossref","unstructured":"Dai, X., Chen, Y., Yang, J., Zhang, P., Yuan, L., Zhang, L.: Dynamic DETR: end-to-end object detection with dynamic attention. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp.\u00a02988\u20132997 (2021)","DOI":"10.1109\/ICCV48922.2021.00298"},{"key":"1761_CR31","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DERE: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"1761_CR32","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., Zhang, L.: DN-DERR: accelerate DERR training by introducing query denoising. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.\u00a013619\u201313627 (2022)","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"1761_CR33","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., Chen, J.: DETRs beat YOLOs on real-time object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.\u00a016965\u201316974, (2024)","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"1761_CR34","unstructured":"Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., Ding, G.: Yolov10: real-time end-to-end object detection. arXiv preprint arXiv:2405.14458 (2024)"},{"key":"1761_CR35","doi-asserted-by":"crossref","unstructured":"Akyon, F.C., Altinuc, S.O., Temizel, A.: slicing aided hyper inference and fine-tuning for small object detection. In: 2022 IEEE International Conference on Image Processing (ICIP), pp.\u00a0966\u2013970, IEEE (2022)","DOI":"10.1109\/ICIP46576.2022.9897990"},{"key":"1761_CR36","unstructured":"Lyu, C., Zhang, W., Huang, H., Zhou, Y., Wang, Y., Liu, Y., Zhang, S., Chen, K.: RTMDet: an empirical study of designing real-time object detectors. arXiv preprint arXiv:2212.07784, (2022)"},{"key":"1761_CR37","unstructured":"Yao, Z., Ai, J., Li, B., Zhang, C.: Efficient DERE: improving end-to-end object detector with dense prior. arXiv preprint arXiv:2104.01318 (2021)"},{"key":"1761_CR38","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Yeh, I.-H., Mark\u00a0Liao, H.-Y.: YOLOv9: Learning what you want to learn using programmable gradient information. In: European Conference on Computer Vision, pp.\u00a01\u201321, Springer, (2025)","DOI":"10.1007\/978-3-031-72751-1_1"},{"issue":"10","key":"1761_CR39","doi-asserted-by":"publisher","first-page":"523","DOI":"10.3390\/drones8100523","volume":"8","author":"S Wang","year":"2024","unstructured":"Wang, S., Jiang, H., Yang, J., Ma, X., Chen, J.: AMFEF-DETR: an end-to-end adaptive multi-scale feature extraction and fusion object detection network based on UAV aerial images. Drones 8(10), 523 (2024)","journal-title":"Drones"},{"key":"1761_CR40","unstructured":"Khanam, R., Hussain, M.: Yolov11: an overview of the key architectural enhancements. arXiv preprint arXiv:2410.17725 (2024)"},{"key":"1761_CR41","doi-asserted-by":"crossref","unstructured":"Meng, D., Chen, X., Fan, Z., Zeng, G., Li, H., Yuan, Y., Sun, L., Wang, J.: Conditional DETR for fast training convergence. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp.\u00a03651\u20133660 (2021)","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"1761_CR42","unstructured":"Liu, S., Li, F., Zhang, H., Yang, X., Qi, X., Su, H., Zhu, J., Zhang, L.: DAB-DERE: dynamic anchor boxes are better queries for DERE. arXiv preprint arXiv:2201.12329 (2022)"},{"issue":"22","key":"1761_CR43","doi-asserted-by":"publisher","first-page":"10331","DOI":"10.3390\/app142210331","volume":"14","author":"H Zhang","year":"2024","unstructured":"Zhang, H., Ma, Z., Li, X.: RS-DERE: an improved remote sensing object detection model based on RT-DERE. Appl. Sci. 14(22), 10331 (2024)","journal-title":"Appl. Sci."}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-025-01761-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-025-01761-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-025-01761-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T14:39:09Z","timestamp":1759761549000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-025-01761-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,12]]},"references-count":43,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["1761"],"URL":"https:\/\/doi.org\/10.1007\/s11554-025-01761-4","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,12]]},"assertion":[{"value":"18 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We affirm that no financial interests, commercial affiliations, or other potential conflict of interest have influenced the integrity of this research or the writing of this paper. The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interests"}}],"article-number":"186"}}